1import duckdb, sys2con = duckdb.connect(sys.argv[1] + "/data/processed/wp44.duckdb", read_only=True)3q = lambda s: con.execute(s).fetchall()4print("eligible by source_type:", q("select source_type, count(*) n, sum(in_dblp::int) dblp, sum((arxiv_id_linked is not null)::int) arx, sum(has_abstract::int) ab, sum((n_refs>0)::int) refs from corpus_works where eligible group by 1 order by 2 desc"))5print("repository sources top 15:", q("select source_name, count(*) n, sum(in_dblp::int) dblp, sum((arxiv_id_linked is not null)::int) arx, sum((n_refs>0)::int) refs, sum(has_abstract::int) ab from corpus_works where eligible and source_type='repository' group by 1 order by 2 desc limit 15"))6print("Zenodo by year:", q("select publication_year, count(*), sum((n_refs>0)::int) refs, sum(has_abstract::int) ab, sum(in_dblp::int) dblp from corpus_works where eligible and source_name like 'Zenodo%' group by 1 order by 1"))7print("Zenodo 2026 sample:", q("select substr(title,1,70), type, n_refs, has_abstract, n_authors, language from corpus_works where eligible and source_name like 'Zenodo%' and publication_year=2026 using sample 8"))8print("NULL-source by year:", q("select publication_year, count(*), sum((n_refs>0)::int) refs, sum(has_abstract::int) ab, sum(in_dblp::int) dblp, sum((type='dissertation')::int) diss from corpus_works where eligible and source_id is null group by 1 order by 1"))9print("NULL-source 2025 sample:", q("select substr(title,1,60), type, n_refs, has_abstract, n_locations, indexed_in from corpus_works where eligible and source_id is null and publication_year=2025 using sample 8"))10print("day-01-01 share by year:", q("select publication_year, round(sum((substr(publication_date,6,5)='01-01')::int)*1.0/count(*),3) from corpus_works where eligible group by 1 order by 1"))11